Deep learning for graph-structured data

In this chapter, we discuss the application of deep learning techniques to input data that exhibit a graph structure. We consider both the case in which the input is a single, huge graph (e.g., a social network), where we are interested in predicting the properties of single nodes (e.g., users), and the case in which the dataset is composed of many small graphs where we want to predict the properties of whole graphs (e.g., molecule property prediction). We discuss the main components required to define such neural architectures and their alternative definitions in the literature. Finally, we present experimental results comparing the main graph neural networks in the literature.